Self-Supervised Learning of Neural Speech Representations From Unlabeled Intracranial Signals

Self-Supervised Learning of Neural Speech Representations From Unlabeled Intracranial Signals

Neuroprosthetics have demonstrated the potential to decode speech from intracranial brain signals, and hold promise for one day returning the ability to speak to those who have lost it. However, data in this domain is scarce, highly variable, and costly to label for supervised modeling. In order to...

Full description

Bibliographic Details
Main Authors: Srdjan Lesaja, Morgan Stuart, Jerry J. Shih, Pedram Z. Soroush, Tanja Schultz, Milos Manic, Dean J. Krusienski
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Brain–computer interface
intracranial EEG
deep learning
transformers
vector quantization
speech modeling
Online Access:https://ieeexplore.ieee.org/document/9992205/

Internet

https://ieeexplore.ieee.org/document/9992205/

Similar Items